2D APPARATUS FOR WELD BEAD RECOGNITION OF 2D IMAGE-BASED AND SOOT REMOVAL METHOD USING THE SAME

摘要

The present invention relates to a 2D image-based welding bead recognition device and a soot removing method using the same. The welding bead recognition device according to the present invention includes an image input unit for receiving a 2D image of an inspection target sample photographed from a vision camera, a preprocessing unit for setting an ROI of the received image, and preprocessing the set ROI, and a preprocessed ROI. An area detection unit for detecting the weld bead area of the sample to be inspected in the area, and removing the weld soot by converting the color coordinates of the detected weld bead area, and binarizing the weld bead area from which the weld soot is removed and the remaining background area. An image acquisition unit for obtaining a binarized image, a weld bead recognition unit for recognizing a weld bead, and feature information of the recognized weld bead are detected from the binarized image obtained by using a morphology algorithm. It includes a determination unit for determining whether or not the shape of the bead. As described above, according to the present invention, it is possible to improve the recognition performance of the weld bead by removing the soot generated between the welding tip and the base material due to the high heat during welding in the 2D image photographed from the vision camera, thereby reducing the error rate when determining the defect inspection. Can be.